{ "io_domain": { "input_subdomain": [ { "uri": { "access_time": "", "sha1_chksum": "", "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/human_protein_masterlist.csv", "filename": "human_protein_masterlist.csv" } }, { "uri": { "access_time": "", "sha1_chksum": "", "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/human_protein_mutation_literature.csv", "filename": "human_cancer_mutation_literature.csv" } }, { "uri": { "access_time": "", "sha1_chksum": "", "uri": "https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/human_protein_mutation_somatic.csv", "filename": "human_cancer_mutation_somatic.csv" } }, { "uri": { "access_time": "", "sha1_chksum": "", "uri": "https://data.glygen.org//ln2downloads/biomuta/v-3.0/mutid-map.final.csv", "filename": "mutid-map.final.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "access_time": "", "sha1_chksum": "", "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_cancer.csv", "filename": "human_protein_mutation_cancer.csv" } }, { "mediatype": "csv", "uri": { "access_time": "", "sha1_chksum": "", "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_cancer.stat.csv", "filename": "human_protein_mutation_cancer.stat.csv" } } ] }, "bco_spec_version": "1.3.0", "checksum": "74bcf99eaaf7d47790985245774749ed", "extension_domain": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "fhir_extension": [], "scm_extension": { "scm_repository": "", "scm_path": "", "scm_type": "git", "scm_commit": "" }, "dataset_categories": [ { "category_value": "Homo sapiens", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Somatic Cancer Mutations", "category_name": "tags" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] }, "provenance_domain": { "license": "https://creativecommons.org/licenses/by/4.0/", "name": "Human Cancer Mutation", "contributors": [ { "orcid": "", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "orcid": "", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Rahi Navelkar", "email": "rsn13@gwu.edu" }, { "orcid": "", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "orcid": "", "affiliation": "BioMuta - The George Washington University", "contribution": [ "importedFrom" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "orcid": "", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "orcid": "", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Amanda Bell", "email": "amandab2140@gwu.edu" }, { "orcid": "", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jonathon Keeney", "email": "keeneyjg@gwu.edu" }, { "orcid": "", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Millicent Quartey", "email": "mquartey@email.gwu.edu" }, { "orcid": "", "affiliation": "", "contribution": [ "contributedBy" ], "name": "Not Applicable", "email": "" } ], "created": "2019-01-23T17:21:05.891293", "modified": "2022-01-12T16:00:11.801720", "version": "1.11.2" }, "description_domain": { "keywords": [ "single-nucleotide variations (nsSNVs)", "cancer mutations", "BioMuta", "disease" ], "pipeline_steps": [ { "name": "make-protein-dataset.py", "step_number": 1, "version": "", "input_list": [ { "access_time": "", "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv", "filename": "human_protein_masterlist.csv" }, { "access_time": "", "uri": "https://data.glygen.org/ln2wwwdata/source/mutid-map.final.csv", "filename": "mutid-map.final.csv" }, { "access_time": "", "sha1_chksum": "", "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_cancer_mutation_literature.csv", "filename": "human_cancer_mutation_literature.csv" }, { "access_time": "", "sha1_chksum": "", "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_cancer_mutation_somatic.csv", "filename": "human_cancer_mutation_somatic.csv" }, { "access_time": "", "sha1_chksum": "", "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_cancer_mutation_literature.csv", "filename": "human_cancer_mutation_literature.csv" } ], "output_list": [ { "access_time": "2019-07-26T17:45:17-0500", "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_cancer.csv", "filename": "human_protein_mutation_cancer.csv" } ], "prerequisite": [], "description": "The script extracts the mutation data from the BioMuta and maps the UniProtKB accession to the UniProtKB canonical accessions as per the criterias" } ] }, "execution_domain": { "external_data_endpoints": [], "environment_variables": {}, "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "access_time": "2019-01-07T17:43:17-0500", "sha1_chksum": "", "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "script": [ { "uri": { "access_time": "2019-07-26T17:43:17-0500", "sha1_chksum": "", "uri": "https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {}, "emperical_error": {} }, "parametric_domain": [ { "step": "", "value": "", "param": "" } ], "usability_domain": [ "The Human Cancer Mutation dataset contains human [taxid:9606] mutation data from BioMuta database (https://hive.biochemistry.gwu.edu/biomuta).", "The current version of BioMuta contains only nonsynonymous single-nucleotide variations (nsSNVs) associated with cancer.", "BioMuta is a single-nucleotide variation (SNV) and disease association database where variations are mapped to genomes and NCBI RefSeq nucleotide entries, and unified through UniProtKB/Swiss-Prot positional coordinates.", "The dataset is imported and contributed by BioMuta and processed by GlyGen. If you use this dataset please provide proper attribution to BioMuta and GlyGen. ", "Note the mutation shown in GlyGen are annotated based on passing of one or more filter criterias.", "Filter criteria 1 - Positive Patient's Frequency Ratio \u2265 1.0%", "Filter criteria 2 - Presence of mutation in number of cancer types \u2265 3 cancer types", "Filter criteria 3 - Positive Patient's count \u2265 10 patients", "Filter criteria 4 - Mutation reported and annotated in number of databases", "Filter criteria 5 - Mutation minned from the literature using literaure mining tools (human_protein_mutation_literature.csv)", "If there is also a germline mutation reported in dbSNP, the rsid is also shown", "These filter criteria annotations are shown on the front end under the column Annotation Name", "Also if the same mutation in the same cancer type on a given protein is reported in ICGC and TCGA then mutations from TCGA are only shown.", "When mutations from TCGA are not available but are present in ICGC for the same protein and cancer type, ICGC mutations are shown in GlyGen", "Two different DO child terms are merged into one single entry showing the parent cancer DO term from the DO cancer slim.", "On the GlyGen interface, in Mutations section the mutations that have passed highest number of filter criteria are displayed first irrespective of their amio acid positions. For eg. the mutation entry that has passed 5 filter criteria will be shown first." ], "_id": { "$oid": "5c48e8d1f5c47b65ae4b5d03" }, "bco_id": "http://data.glygen.org/GLY_000024" }